• 한국전자통신학회논문지
• /
• 제8권10호
• /
• pp.1529-1534
• /
• 2013

NAND 플래쉬메모리는 적은 크기로 대용량의 데이터를 저장할 수 있고 전력소모량이 적기 때문에 스마트 폰, 센서노드 등의 다양한 휴대용기기에서 사용되어 진다. 플래쉬메모리에 저장된 대용량의 데이터를 효율적으로 처리하기 위하여 색인을 사용해야 한다. 그러나 쓰기 연산의 속도가 읽기 연산보다 매우 느리고 덮어쓰기를 지원하지 않기 때문에 기존의 색인을 사용하면 성능이 저하되는 문제가 발생한다. 이 논문에서는 플래쉬메모리의 특성을 이용하여 색인을 설계한 기존의 논문들을 살펴본다. 그리고 플래쉬메모리에서 색인을 설계할 때 고려해야할 성능요소를 제시한다.

• 대한전자공학회논문지SD
• /
• 제44권4호
• /
• pp.43-54
• /
• 2007

본 논문에서는 실시간 처리를 위한 얼굴 검출 알고리즘의 하드웨어 엔진을 설계하고 검증하였다. 얼굴 검출 알고리즘은 주어진 이미지에서 학습된 얼굴의 특징데이터를 통하여 얼굴의 대략적인 위치를 찾는 연산을 수행한다. 얼굴 검출 알고리즘을 하드웨어 구조로 설계하기 위해 Integral Image Calculator, Feature Coordinate Calculator, Feature Difference Calculator, Cascade Calculator, Window Detector 등의 5 단계로 구조를 나누었으며, On-Chip Integral Image memory 와 Feature Parameter Memory를 설계하였다. 삼성전자의 S3C2440A 프로세서 칩과 Xilinx사의 Virtex4LX100을 이용하여 검증 플랫폼을 구축하고, CCD카메라를 통하여 실제 얼굴의 영상을 받아들여 얼굴 검출을 실시간으로 구동시켜 검증하였다. 설계된 하드웨어는 Virtex4LX100 FPGA를 타겟으로 합성 시에 3,251 LUTs 를 사용하고, 24MHz의 동작 속도에서 검색 윈도우의 이동 간격에 따라 프레임 당 1.96$\sim$0.13 초의 실행속도를 가진다. 그리고 매그나칩 0.25um ASIC 공정으로 제작 시 41만 게이트 (Combinational area 약 34.5만 게이트, Noncombinational area 약 6.5만 게이트)의 크기를 가지며, 100MHz의 동작 속도에서 프레임 당 0.5초 미만의 실행 속도로, 임베디드 시스템의 실시간 얼굴 검출 솔루션에 적합함을 보여준다. 실제 XF1201칩의 일부 모듈로 구현되어 동작함이 확인되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.695-698
• /
• 1998

Today SOC(system on a chip) is a trend in VLSI design society. Especially MML(merged memory Logic) process provides designers with good chances to implement SOC which is consists of DRAM, SRAM, Logic and A/D mixed mode ciruit blocks. Designers need good circuit library which is reliable and easy to tune for specific design. For this need we present semi-automated analog compiler methodology. And we aplied this design methodology to resistor-string DAC design.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.1137-1140
• /
• 1999

In this thesis, we research about Communication System Construction and Test-Bed Realization Method and Software’s Design with written program into Embedded Micro Controller’s restricted memory region using a DSP Chip to deal with mainly high speed communication. Tools used for modern communication network control use TI or AMD general chip class, but nevertheless responsibility for the point at issue, Analog Device is architecture design model moderated for small communication system. In this thesis, we present extended model, and realize basic case.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2240-2243
• /
• 2003

In this paper. we present a new speech recognition system using DSP chip. DSP chip used TMS320c6711 of TI. We designed hardware system including acoustic model, word list and code book in flash memory. The word candidates are recognized based on CV, VCCV, and VC units HMM. This system can be applied to various electric ＆ electronic devices: home automation, robotics etc.

• 한국마이크로전자및패키징학회:학술대회논문집
• /
• 한국마이크로전자및패키징학회 2005년도 ISMP
• /
• pp.111-129
• /
• 2005

Pop provides OEMs and EMS with a platform to cost effectively expand options for logic + memory 3D integration - Expands device options by simplifying business logistics of stacking - Integration controlled at the system level to best match stacked combinations with system requirements - Eliminates margin stacking and expands technology reuse - Helps manage the huge cost impacts associated with increasing demand for multi media processing and memory. PoP is well timed to enable and leverage: - Mass customization of systems for different use (form, fit and function) requirements o Bband and apps processor + memory stack platforms - Logic transition to flip chip enables PoP size reduction o Area and height reduction. Industry standardization is progressing. Amkor provides full turn-key support for base package, memory package and full system integration.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2004년도 추계학술대회 논문집 Vol.17
• /
• pp.53-56
• /
• 2004

This paper presents the improved burn-in method for the reliability of SRAM in MCP Semiconductor reliability is commonly improved through the burn-in process. Reliability problem is more significant in the Multi Chip Package, because of including over two devices in a package. In the SRAM-based Multi Chip Package, the failure of SRAM has a large effect on the yield and quality of the other chips - Flash Memory, DRAM, etc. So, the quality of SRAM must be guaranteed. To improve the quality of SRAM, we applied the improved wafer level burn-in process using multi cell selection method in addition to the current used methods. That method is effective in detecting special failure. Finally, with the composition of some kinds of methods, we could achieve the high qualify of SRAM in Multi Chip Package.

• 전기학회논문지
• /
• 제68권2호
• /
• pp.364-369
• /
• 2019

Generally, since memory chips should be tested all, considering its volume, the reduction in test time for detecting faults plays an important role in reducing the overall production cost. The parallel testing of chips in one ATE is a competitive solution to solve it. In this paper, NOC is proposed as test interface architecture between DUTs and ATE. Because NOC can be extended freely, there is no limit on the number of DUTs tested at the same time. Thus, more memory can be tested with the same bandwidth of ATE. Furthermore, the proposed NOC-based parallel test method can increase the efficiency of channel usage by packet type data transmission.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (1)
• /
• pp.196-198
• /
• 2003

Virtually every digital signal processors(DSPs) support on-chip multi- memory banks that allow the processor to access multiple words of data from memory in a single instruction cycle. Also, all existing fixed-point DSPs have irregular architecture of heterogeneous register which contains multiple register files that are distributed and dedicated to different sets of instructions. Although there have been several studies conducted to efficiently assign data to multi-memory banks, most of them assumed processors with relatively simple, homogeneous general-purpose resisters. Therefore, several vendor-provided compilers fer DSPs were unable to efficiently assign data to multiple data memory banks. thereby often failing to generate highly optimized code fer their machines. This paper presents an algorithm that helps the compiler to efficiently assign data to multi- memory banks. Our algorithm differs from previous work in that it assigns variables to memory banks in separate, decoupled code generation phases, instead of a single, tightly-coupled phase. The experimental results have revealed that our decoupled algorithm greatly simplifies our code generation process; thus our compiler runs extremely fast, yet generates target code that is comparable In quality to the code generated by a coupled approach

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권8호
• /
• pp.578-584
• /
• 2004

The CSVM(Current Support Vector Machine) that is a digital architecture performing all phases of recognition process including kernel computing, learning, and recall of SVM(Support Vector Machine) on a chip is proposed. Concurrent operation by parallel architecture of elements generates high speed and throughput. The classification problems of bio data having high dimension are solved fast and easily using the CSVM. Quadratic programming in original SVM learning algorithm is not suitable for hardware implementation, due to its complexity and large memory consumption. Hardware-friendly SVM learning algorithms, kernel adatron and kernel perceptron, are embedded on a chip. Experiments on fixed-point algorithm having quantization error are performed and their results are compared with floating-point algorithm. CSVM implemented on FPGA chip generates fast and accurate results on high dimensional cancer data.